AI Paper Atlas

Research map / Adversarial robustness and security / Certified and empirical robustness

Boosting the Robustness-Accuracy Trade-off of SNNs by Robust Temporal Self-Ensemble

Jihang Wang, Dongcheng Zhao, Ruolin Chen, Qian Zhang, Yi Zeng

AAAI 2026 · Adversarial robustness and security › Certified and empirical robustness · approach: Robustness-accuracy trade-off analysis · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use RTE instead of TRADESSNN adversarial training · CIFAR-100 (T=4)clean accuracy (%): 56.97 -> 59.50Improved
use RTE instead of TRADESSNN adversarial training · Tiny-ImageNet (T=4)clean accuracy (%): 47.76 -> 50.46Improved
use RTE instead of TRADESSNN adversarial training · SVHN (T=4)clean accuracy (%): 94.00 -> 93.59Hurt
use RTE instead of ATSNN adversarial training · CIFAR-100 (T=4)APGD-CE robust accuracy (%): 13.08 -> 17.77Improved
combine RTE with SR (sparsity regularization) (ablation)RTE · CIFAR-100 (T=4)APGD-CE robust accuracy (%): 17.77 -> 20.18Improved
combine RTE with SR (ablation)RTE · CIFAR-100 (T=4)clean accuracy (%): 59.50 -> 58.10Hurt
use RTE+SR instead of AT+SRAT+SR · CIFAR-10 (T=4)worst-case robust accuracy: -0.90 (text)Hurt
use RTE+SR instead of AT+SRAT+SR · CIFAR-10 (T=4)clean accuracy (%): 78.55 -> 80.85Improved
RTE+SR vs strongest baseline on trade-off metric (clean+robust)baselines · CIFAR-100 and Tiny-ImageNetclean + robust accuracy: +3.92 and +4.80 pointsImproved
increase timesteps T from 4 to 12 (ablation)AT, RAT, TRADES, RTE · CIFAR-10/100robustness-accuracy trade-offImproved
vary regularization gamma: RTE vs TRADES (ablation)RTE · CIFAR-10/100trade-off (clean+robust)Improved
add RTE vs AT/RAT/TRADES in transferability matricesRTE · CIFAR-10 T=8KL transferabilityImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy